Chapter 8 Differential abundance analysis
8.1 CC acclimation vs post2
8.1.1 Enrichment analysis: Ancombc2
8.1.1.1 Structural zeros
# A tibble: 181 × 14
# Rowwise:
genome present average domain phylum class order family genus species completeness contamination length gc
<chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 AH1_2nd_11:bin_000008 accli 6.79 d__Bacteria p__Verrucomicrobiota c__Verrucomicrobiae o__Verrucomicrobiales f__Akkermansiaceae g__Akkermansia s__ 100 0.12 3054831 0.58
2 AH1_2nd_1:bin_000039 accli 5.96 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Marinifilaceae g__Odoribacter s__ 99.5 0.1 3918820 0.44
3 AH1_2nd_17:bin_000010 accli 2.61 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Rikenellaceae g__Mucinivorans s__ 98.1 0.06 2365004 0.44
4 AH1_2nd_17:bin_000038 accli 2.42 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Bacteroidaceae g__Bacteroides_G s__ 88.0 3.29 4258067 0.4
5 AH1_2nd_14:bin_000005 accli 2.19 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__ s__ 97.1 0.82 3930509 0.3
6 AH1_2nd_5:bin_000002 accli 1.63 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Marinifilaceae g__Odoribacter s__ 99.6 0.04 3603552 0.45
7 AH1_2nd_12:bin_000015 accli 1.52 d__Bacteria p__Bacillota c__Bacilli o__Erysipelotrichales f__Coprobacillaceae g__Thomasclavelia s__ 100 7.76 3794096 0.31
8 AH1_2nd_8:bin_000020 accli 1.25 d__Bacteria p__Pseudomonadota c__Alphaproteobacteria o__RUG11792 f__RUG11792 g__ s__ 99.6 0 892810 0.36
9 AH1_2nd_1:bin_000028 accli 1.15 d__Bacteria p__Pseudomonadota c__Alphaproteobacteria o__Rickettsiales f__UBA1997 g__CALXRO01 s__ 98.0 0 935376 0.28
10 AH1_2nd_12:bin_000063 accli 0.911 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__CHH4-2 s__ 72.2 2.05 3506133 0.42
# ℹ 171 more rows
8.2 CC acclimation vs post1
8.2.1 Enrichment analysis: Ancombc2
8.2.1.1 Structural zeros
# A tibble: 206 × 14
# Rowwise:
genome present average domain phylum class order family genus species completeness contamination length gc
<chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 AH1_2nd_1:bin_000006 accli 13.1 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__Kineothrix s__ 98.5 4.38 4263353 0.44
2 AH1_2nd_18:bin_000011 accli 10.1 d__Bacteria p__Bacillota c__Bacilli o__Erysipelotrichales f__Coprobacillaceae g__Coprobacillus s__ 98.4 7.24 3675733 0.3
3 AH1_2nd_11:bin_000008 accli 6.79 d__Bacteria p__Verrucomicrobiota c__Verrucomicrobiae o__Verrucomicrobiales f__Akkermansiaceae g__Akkermansia s__ 100 0.12 3054831 0.58
4 AH1_2nd_17:bin_000023 accli 6.31 d__Bacteria p__Bacillota c__Bacilli o__Erysipelotrichales f__Coprobacillaceae g__Coprobacillus s__ 90.2 1.72 3372832 0.31
5 LI1_2nd_4:bin_000026 accli 6.09 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Marinifilaceae g__Odoribacter s__ 99.4 3.28 4761273 0.44
6 AH1_2nd_1:bin_000039 accli 5.96 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Marinifilaceae g__Odoribacter s__ 99.5 0.1 3918820 0.44
7 AH1_2nd_17:bin_000010 accli 2.61 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Rikenellaceae g__Mucinivorans s__ 98.1 0.06 2365004 0.44
8 AH1_2nd_17:bin_000038 accli 2.42 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Bacteroidaceae g__Bacteroides_G s__ 88.0 3.29 4258067 0.4
9 AH1_2nd_20:bin_000016 accli 2.27 d__Bacteria p__Bacillota c__Bacilli o__Erysipelotrichales f__Erysipelotrichaceae g__ s__ 97.5 3.86 4005468 0.37
10 AH1_2nd_14:bin_000005 accli 2.19 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__ s__ 97.1 0.82 3930509 0.3
# ℹ 196 more rows
8.3 WC acclimation vs post2
8.3.1 Enrichment analysis: Ancombc2
8.3.1.1 Structural zeros
# A tibble: 134 × 14
# Rowwise:
genome present average domain phylum class order family genus species completeness contamination length gc
<chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 AH1_2nd_13:bin_000004 accli 2.13 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__ s__ 97.0 0.58 3761779 0.42
2 LI1_2nd_2:bin_000048 accli 2.07 d__Bacteria p__Bacillota c__Bacilli o__Erysipelotrichales f__Coprobacillaceae g__Coprobacillus s__ 86.9 4.89 3159306 0.31
3 AH1_2nd_12:bin_000008 accli 1.99 d__Bacteria p__Bacillota c__Bacilli o__Lactobacillales f__Streptococcaceae g__Lactococcus s__Lactococcus formosensis 99.9 0.2 2049859 0.38
4 LI1_2nd_3:bin_000015 accli 1.98 d__Bacteria p__Bacillota c__Bacilli o__Staphylococcales f__Staphylococcaceae g__Staphylococcus s__Staphylococcus shinii 91.7 3.54 2956427 0.32
5 LI1_2nd_8:bin_000044 accli 1.47 d__Bacteria p__Bacillota_A c__Clostridia o__Oscillospirales f__Ruminococcaceae g__Angelakisella s__ 80.1 3.35 2723215 0.62
6 LI1_2nd_2:bin_000030 accli 1.14 d__Bacteria p__Bacillota c__Bacilli o__RF39 f__UBA660 g__Caccenecus s__ 91.6 1.86 1128677 0.28
7 LI1_2nd_2:bin_000002 accli 1.10 d__Bacteria p__Bacillota_A c__Clostridia o__Oscillospirales f__Ruminococcaceae g__Ruthenibacterium s__ 94.7 2.65 2840729 0.53
8 AH1_2nd_6:bin_000006 accli 1.09 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__JAAYNV01 s__ 99.8 0.57 3690498 0.45
9 LI1_2nd_1:bin_000052 accli 1.07 d__Bacteria p__Bacillota_A c__Clostridia o__TANB77 f__CAG-508 g__RGIG8482 s__ 83.8 7.54 1933783 0.3
10 AH1_2nd_16:bin_000045 accli 1.07 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Rikenellaceae g__Alistipes s__ 93.6 6.68 3445818 0.59
# ℹ 124 more rows
8.4 CI acclimation vs post2
8.4.1 Enrichment analysis: Ancombc2
8.4.1.1 Structural zeros
# A tibble: 195 × 14
# Rowwise:
genome present average domain phylum class order family genus species completeness contamination length gc
<chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 AH1_2nd_1:bin_000006 accli 39.3 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__Kineothrix s__ 98.5 4.38 4263353 0.44
2 LI1_2nd_7:bin_000008 accli 7.37 d__Bacteria p__Bacillota c__Bacilli o__Erysipelotrichales f__Erysipelotrichaceae g__Breznakia s__ 97.9 2.36 2618172 0.3
3 AH1_2nd_18:bin_000013 accli 4.35 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Tannerellaceae g__Parabacteroides s__ 98.7 0.01 4005076 0.43
4 AH1_2nd_20:bin_000004 accli 2.87 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__Roseburia s__ 100. 0.43 3729496 0.42
5 AH1_2nd_5:bin_000054 accli 2.45 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Bacteroidaceae g__Bacteroides s__ 86.4 3.24 5336241 0.43
6 AH1_2nd_1:bin_000001 accli 1.71 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Tannerellaceae g__Parabacteroides_B s__ 99.6 1.94 4534617 0.51
7 AH1_2nd_20:bin_000061 accli 1.69 d__Bacteria p__Bacillota c__Bacilli o__Lactobacillales f__Enterococcaceae g__Enterococcus s__ 92.6 6.02 4153944 0.4
8 AH1_2nd_16:bin_000008 accli 1.59 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__ g__ s__ 98.4 0.14 3874322 0.28
9 LI1_2nd_3:bin_000007 accli 1.48 d__Bacteria p__Bacillota c__Bacilli o__Erysipelotrichales f__Erysipelotrichaceae g__C-19 s__ 99.8 1.24 3665262 0.36
10 AH1_2nd_10:bin_000044 accli 1.20 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__Enterocloster s__ 88.9 0.53 3623272 0.48
# ℹ 185 more rows
8.5 CI acclimation vs post1
8.5.1 Enrichment analysis: Ancombc2
8.5.1.1 Structural zeros
# A tibble: 223 × 14
# Rowwise:
genome present average domain phylum class order family genus species completeness contamination length gc
<chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 AH1_2nd_1:bin_000006 accli 39.3 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__Kineothrix s__ 98.5 4.38 4263353 0.44
2 AH1_2nd_19:bin_000005 accli 24.7 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__Roseburia s__ 96.1 0.16 3941649 0.42
3 AH1_2nd_13:bin_000004 accli 11.5 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__ s__ 97.0 0.58 3761779 0.42
4 AH1_2nd_11:bin_000008 accli 9.27 d__Bacteria p__Verrucomicrobiota c__Verrucomicrobiae o__Verrucomicrobiales f__Akkermansiaceae g__Akkermansia s__ 100 0.12 3054831 0.58
5 AH1_2nd_19:bin_000001 accli 8.34 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Tannerellaceae g__Parabacteroides s__ 99.7 1.43 4736923 0.51
6 AH1_2nd_19:bin_000038 accli 8.08 d__Bacteria p__Pseudomonadota c__Alphaproteobacteria o__RUG11792 f__ g__ s__ 94.6 0 932470 0.37
7 LI1_2nd_7:bin_000008 accli 7.37 d__Bacteria p__Bacillota c__Bacilli o__Erysipelotrichales f__Erysipelotrichaceae g__Breznakia s__ 97.9 2.36 2618172 0.3
8 AH1_2nd_18:bin_000047 accli 6.98 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Tannerellaceae g__Parabacteroides s__ 87.5 4.81 5473283 0.43
9 AH1_2nd_9:bin_000015 accli 6.88 d__Bacteria p__Desulfobacterota c__Desulfovibrionia o__Desulfovibrionales f__Desulfovibrionaceae g__Desulfovibrio s__ 99.0 0 3043039 0.61
10 AH1_2nd_10:bin_000007 accli 6.07 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__ g__ s__ 97.5 0.68 3552238 0.29
# ℹ 213 more rows
8.6 post2 CC and CI
8.6.1 Enrichment analysis: Ancombc2
8.6.1.1 Structural zeros
# A tibble: 174 × 14
# Rowwise:
genome present average domain phylum class order family genus species completeness contamination length gc
<chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 AH1_2nd_18:bin_000013 cc_post2 36.2 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Tannerellaceae g__Parabacteroides s__ 98.7 0.01 4005076 0.43
2 AH1_2nd_15:bin_000002 cc_post2 7.12 d__Bacteria p__Cyanobacteriota c__Vampirovibrionia o__Gastranaerophilales f__Gastranaerophilaceae g__Limenecus s__ 99.8 0.87 2111746 0.37
3 LI1_2nd_7:bin_000001 cc_post2 4.42 d__Bacteria p__Bacillota_A c__Clostridia o__Clostridiales f__Clostridiaceae g__Sarcina s__ 98.3 1.37 3938038 0.28
4 AH1_2nd_9:bin_000061 cc_post2 4.33 d__Bacteria p__Pseudomonadota c__Gammaproteobacteria o__Burkholderiales f__Burkholderiaceae_C g__Alcaligenes s__ 72.8 6.01 3338181 0.57
5 AH1_2nd_7:bin_000015 cc_post2 3.75 d__Bacteria p__Pseudomonadota c__Alphaproteobacteria o__RF32 f__CAG-239 g__CAZU01 s__ 100 0.49 1794016 0.43
6 AH1_2nd_1:bin_000001 cc_post2 2.77 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Tannerellaceae g__Parabacteroides_B s__ 99.6 1.94 4534617 0.51
7 AH1_2nd_7:bin_000006 cc_post2 1.87 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__JALFVM01 s__ 100 2.39 4970285 0.43
8 AH1_2nd_7:bin_000065 cc_post2 1.49 d__Bacteria p__Bacteroidota c__Bacteroidia o__Bacteroidales f__Tannerellaceae g__Parabacteroides s__ 93.7 2.1 5263338 0.43
9 AH1_2nd_7:bin_000038 cc_post2 1.47 d__Bacteria p__Bacillota_A c__Clostridia o__Oscillospirales f__Ruminococcaceae g__ s__ 91.7 4.31 2931073 0.49
10 AH1_2nd_19:bin_000017 cc_post2 1.35 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__Caccomorpha s__ 92.8 4.49 5611813 0.47
# ℹ 164 more rows
8.7 post2 WC and CI
8.7.1 Enrichment analysis: Ancombc2
####Structural zeros
# A tibble: 161 × 14
# Rowwise:
genome present average domain phylum class order family genus species completeness contamination length gc
<chr> <chr> <dbl> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl>
1 AH1_2nd_14:bin_000015 ci_post2 17.8 d__Bacteria p__Bacillota_A c__Clostridia o__Christensenellales f__UBA3700 g__ s__ 94.8 0 2023163 0.36
2 AH1_2nd_1:bin_000028 ci_post2 4.77 d__Bacteria p__Pseudomonadota c__Alphaproteobacteria o__Rickettsiales f__UBA1997 g__CALXRO01 s__ 98.0 0 935376 0.28
3 AH1_2nd_12:bin_000041 ci_post2 4.76 d__Bacteria p__Bacillota c__Bacilli o__Mycoplasmatales f__Mycoplasmoidaceae g__Mycoplasmoides s__ 92.6 0.18 1005235 0.27
4 AH1_2nd_8:bin_000020 ci_post2 4.34 d__Bacteria p__Pseudomonadota c__Alphaproteobacteria o__RUG11792 f__RUG11792 g__ s__ 99.6 0 892810 0.36
5 AH1_2nd_1:bin_000015 ci_post2 4.10 d__Bacteria p__Bacillota_A c__Clostridia o__Lachnospirales f__Lachnospiraceae g__MGBC136627 s__ 96.6 0.56 3882618 0.33
6 AH1_2nd_19:bin_000052 ci_post2 3.95 d__Bacteria p__Verrucomicrobiota c__Verrucomicrobiae o__Opitutales f__LL51 g__ s__ 92.8 0 889473 0.53
7 AH1_2nd_2:bin_000034 ci_post2 3.09 d__Bacteria p__Verrucomicrobiota c__Verrucomicrobiae o__Opitutales f__LL51 g__ s__ 93.8 0 862378 0.56
8 AH1_2nd_6:bin_000001 ci_post2 2.21 d__Bacteria p__Bacteroidota c__Bacteroidia o__Flavobacteriales f__Weeksellaceae g__Moheibacter s__ 98.7 0.1 3381883 0.36
9 AH1_2nd_10:bin_000009 ci_post2 1.72 d__Bacteria p__Desulfobacterota c__Desulfovibrionia o__Desulfovibrionales f__Desulfovibrionaceae g__Bilophila s__ 97.9 0.61 3772750 0.51
10 AH1_2nd_5:bin_000037 ci_post2 1.67 d__Bacteria p__Bacillota_A c__Clostridia o__Oscillospirales f__Oscillospiraceae g__Pseudoflavonifractor s__ 93.4 7.74 3923478 0.58
# ℹ 151 more rows
8.8 Community level plots
accli_post2<-sample_metadata%>%
filter(time_point == "1_Acclimation"|time_point == "6_Post-FMT2")
accli_post2$newID<-paste(accli_post2$type, "_", accli_post2$time_point)
GIFTs_functions_community %>%
as.data.frame() %>%
rownames_to_column("sample") %>%
left_join(accli_post2, by = join_by(sample == Tube_code)) %>%
filter(time_point == "1_Acclimation"|time_point == "6_Post-FMT2") %>%
select(c(1:29, 36,39)) %>%
pivot_longer(-c(sample,type,time_point),names_to = "trait", values_to = "value") %>%
mutate(trait = case_when(
trait %in% GIFT_db3$Code_function ~ GIFT_db3$Function[match(trait, GIFT_db3$Code_function)],
TRUE ~ trait
)) %>%
mutate(trait=factor(trait,levels=unique(GIFT_db3$Function))) %>%
ggplot(aes(x=value, y=time_point, group=time_point, fill=type, color=type)) +
geom_boxplot() +
scale_color_manual(name="type",
breaks=c("Control","Hot_control", "Treatment"),
labels=c("Cold-Cold","Hot-Hot", "Cold-Hot"),
values=c("#4477AA","#d57d2c","#76b183")) +
scale_fill_manual(name="type",
breaks=c("Control","Hot_control", "Treatment"),
labels=c("Cold-Cold","Hot-Hot", "Cold-Hot"),
values=c("#4477AA50","#d57d2c50","#76b18350")) +
facet_grid(trait ~ type, space="free", scales="free") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1),
strip.text.y = element_text(angle = 0)) +
labs(y="Traits",x="Metabolic capacity index")
GIFTs_elements_community_merged<-GIFTs_elements_community %>%
as.data.frame() %>%
rownames_to_column(var="sample") %>%
filter(sample!="AD69") %>%
pivot_longer(!sample,names_to="trait",values_to="gift") %>%
left_join(sample_metadata, by = join_by(sample == Tube_code))%>%
filter(time_point=="1_Acclimation"|time_point == "6_Post-FMT2")%>%
mutate(functionid = substr(trait, 1, 3)) %>%
mutate(trait = case_when(
trait %in% GIFT_db3$Code_element ~ GIFT_db3$Element[match(trait, GIFT_db3$Code_element)],
TRUE ~ trait
)) %>%
mutate(functionid = case_when(
functionid %in% GIFT_db3$Code_function ~ GIFT_db3$Function[match(functionid, GIFT_db3$Code_function)],
TRUE ~ functionid
)) %>%
mutate(trait=factor(trait,levels=unique(GIFT_db3$Element))) %>%
mutate(functionid=factor(functionid,levels=unique(GIFT_db3$Function)))
# Create an interaction variable for time_point and sample
GIFTs_elements_community_merged$interaction_var <- interaction(GIFTs_elements_community_merged$sample, GIFTs_elements_community_merged$time_point)
ggplot(GIFTs_elements_community_merged,aes(x=interaction_var,y=trait,fill=gift)) +
geom_tile(colour="white", linewidth=0.2)+
scale_fill_gradientn(colours=rev(c("#d53e4f", "#f46d43", "#fdae61", "#fee08b", "#e6f598", "#abdda4", "#ddf1da")))+
facet_grid(functionid ~ type, scales="free",space="free") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1, size=5),
strip.text.y = element_text(angle = 0)) +
labs(y="Traits",x="Time_point",fill="GIFT")+
scale_x_discrete(labels = function(x) gsub(".*\\.", "", x))
8.9 Wilcoxon comparison
8.9.1 Community elements differences: in CC acclimation vs post2
Elements Acclimation Post2 Function Element Difference group_color
1 T0503 0.1830714 0.01253516 Vitamin transport_Niacin (B3) Niacin (B3) 0.1705362 Acclimation
8.9.2 Community elements differences: in CI acclimation vs post2
difference_table_CI %>%
filter(group_color=="Acclimation")
8.9.3 Community elements differences: in WC acclimation vs post2
difference_table_WC %>%
filter(group_color=="Acclimation")
8.9.4 Comparison of both population in wild samples
Elements Acclimation Post2 Function Element Difference group_color
1 T0211 0.07898304 0.03960845 Amino acid transport_Serine Serine 0.03937459 Acclimation
2 T0705 0.03026609 0.01792140 Nucleic acid transport_Allantoin Allantoin 0.01234469 Acclimation
3 T0401 0.08571001 0.03355773 Organic anion transport_Spermidine Spermidine 0.05215228 Acclimation
4 T0406 0.06660075 0.02039130 Organic anion transport_Succinate Succinate 0.04620945 Acclimation
5 D0301 0.03445823 0.02175758 Sugar degradation_Lactose Lactose 0.01270065 Acclimation
6 B0711 0.31689890 0.23431920 Vitamin biosynthesis_Menaquinone (K2) Menaquinone (K2) 0.08257970 Acclimation
7 T0503 0.05906234 0.02697581 Vitamin transport_Niacin (B3) Niacin (B3) 0.03208653 Acclimation
####Butiryc acid biosynthesis
